© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 21185
    Prev
    Next
    INDEX
    Explanations

    references to elephants, particularly related to elephant poaching and ivory

    oai_token-act-pair · gpt-3.5-turbo

    references to elephants and issues related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lly
    -0.80
    nder
    -0.77
    pring
    -0.74
    âĸ¬
    -0.72
    ername
    -0.71
    ndra
    -0.70
    lying
    -0.70
    HER
    -0.69
    nergy
    -0.69
    nerg
    -0.68
    POSITIVE LOGITS
    iasis
    1.33
     elephant
    0.95
     elephants
    0.89
     Haram
    0.84
     ivory
    0.83
    ota
    0.81
    opard
    0.79
     Elephant
    0.77
     herds
    0.76
     calf
    0.75
    Activations Density 0.043%

    No Known Activations